On CorefUD 1.4 with new long-range datasets, CorPipeEnsemble leads at 77.11 CoNLL F1 while the best fine-tuned LLM reaches 74.32, narrowing the prior gap.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Findings of the Fifth Shared Task on Multilingual Coreference Resolution: Expanding Datasets for Long-Range Entities
On CorefUD 1.4 with new long-range datasets, CorPipeEnsemble leads at 77.11 CoNLL F1 while the best fine-tuned LLM reaches 74.32, narrowing the prior gap.